An Empirical Study of Building a Strong Baseline for Constituency Parsing

By Jun Suzuki, Sho Takase, Hidetaka Kamigaito, Makoto Morishita, Masaaki Nagata. 2018

16 citations recorded by the source corpus.

This paper investigates the construction of a strong baseline based on general purpose sequence-to-sequence models for constituency parsing. We incorporate several techniques that were mainly developed in natural language generation tasks, e.g., machine translation and summarization, and demonstrate that the sequence-to-sequence model achieves the current top-notch parsers’ performance (almost) without requiring any explicit task-specific knowledge or architecture of constituent parsing.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jun Suzuki
2. Masaaki Nagata
3. Sho Takase
4. Michael Auli
5. David Grangier

Citations in the corpus

• Direct Output Connection for a High-Rank Language Model (2018, background): “Our base parser has two different parts from Suzuki et al. (2018).”